import pandas as pd
import numpy as np

#to plot the data
import matplotlib.pyplot as plt
import seaborn as sns
plt.style.use('fivethirtyeight')
%matplotlib inline

# Input files don't have column names
dependent_var = ['RUL']
index_columns_names = ["UnitNumber","Cycle"]
operational_settings_columns_names = ['mode1', 'mode2', 'mode3']
sensor_measure_columns_names =['sensor{}'.format(i) for i in range(1, 22)] 
input_file_column_names = index_columns_names + operational_settings_columns_names + sensor_measure_columns_names

#Importing train dataset and calculating remaining useful life



df_train = pd.read_csv('C:\\Users\\Madhu Shree\\OneDrive\\Desktop\\Generative Model\\data\\CMAPSSData\\train_FD001.txt',delim_whitespace=True,names=input_file_column_names)

rul = pd.DataFrame(df_train.groupby('UnitNumber')['Cycle'].max()).reset_index()
rul.columns = ['UnitNumber', 'max']
df_train = df_train.merge(rul, on=['UnitNumber'], how='left')
df_train['RUL'] = df_train['max'] - df_train['Cycle']
df_train.drop('max', axis=1, inplace=True)

C:\Users\Madhu Shree\AppData\Local\Temp\ipykernel_9432\2559281974.py:5: FutureWarning: The 'delim_whitespace' keyword in pd.read_csv is deprecated and will be removed in a future version. Use ``sep='\s+'`` instead
  df_train = pd.read_csv('C:\\Users\\Madhu Shree\\OneDrive\\Desktop\\Generative Model\\data\\CMAPSSData\\train_FD001.txt',delim_whitespace=True,names=input_file_column_names)

df_train.head()

	UnitNumber	Cycle	mode1	mode2	mode3	sensor1	sensor2	sensor3	sensor4	sensor5	...	sensor13	sensor14	sensor15	sensor16	sensor17	sensor18	sensor19	sensor20	sensor21	RUL
0	1	1	-0.0007	-0.0004	100.0	518.67	641.82	1589.70	1400.60	14.62	...	2388.02	8138.62	8.4195	0.03	392	2388	100.0	39.06	23.4190	191
1	1	2	0.0019	-0.0003	100.0	518.67	642.15	1591.82	1403.14	14.62	...	2388.07	8131.49	8.4318	0.03	392	2388	100.0	39.00	23.4236	190
2	1	3	-0.0043	0.0003	100.0	518.67	642.35	1587.99	1404.20	14.62	...	2388.03	8133.23	8.4178	0.03	390	2388	100.0	38.95	23.3442	189
3	1	4	0.0007	0.0000	100.0	518.67	642.35	1582.79	1401.87	14.62	...	2388.08	8133.83	8.3682	0.03	392	2388	100.0	38.88	23.3739	188
4	1	5	-0.0019	-0.0002	100.0	518.67	642.37	1582.85	1406.22	14.62	...	2388.04	8133.80	8.4294	0.03	393	2388	100.0	38.90	23.4044	187

5 rows × 27 columns

#Importing Test dataset

df_test = pd.read_csv('C:\\Users\\Madhu Shree\\OneDrive\\Desktop\\Generative Model\\data\\CMAPSSData\\test_FD001.txt', delim_whitespace=True, names=input_file_column_names)
df_test.head()

C:\Users\Madhu Shree\AppData\Local\Temp\ipykernel_9432\1464558967.py:3: FutureWarning: The 'delim_whitespace' keyword in pd.read_csv is deprecated and will be removed in a future version. Use ``sep='\s+'`` instead
  df_test = pd.read_csv('C:\\Users\\Madhu Shree\\OneDrive\\Desktop\\Generative Model\\data\\CMAPSSData\\test_FD001.txt', delim_whitespace=True, names=input_file_column_names)

	UnitNumber	Cycle	mode1	mode2	mode3	sensor1	sensor2	sensor3	sensor4	sensor5	...	sensor12	sensor13	sensor14	sensor15	sensor16	sensor17	sensor18	sensor19	sensor20	sensor21
0	1	1	0.0023	0.0003	100.0	518.67	643.02	1585.29	1398.21	14.62	...	521.72	2388.03	8125.55	8.4052	0.03	392	2388	100.0	38.86	23.3735
1	1	2	-0.0027	-0.0003	100.0	518.67	641.71	1588.45	1395.42	14.62	...	522.16	2388.06	8139.62	8.3803	0.03	393	2388	100.0	39.02	23.3916
2	1	3	0.0003	0.0001	100.0	518.67	642.46	1586.94	1401.34	14.62	...	521.97	2388.03	8130.10	8.4441	0.03	393	2388	100.0	39.08	23.4166
3	1	4	0.0042	0.0000	100.0	518.67	642.44	1584.12	1406.42	14.62	...	521.38	2388.05	8132.90	8.3917	0.03	391	2388	100.0	39.00	23.3737
4	1	5	0.0014	0.0000	100.0	518.67	642.51	1587.19	1401.92	14.62	...	522.15	2388.03	8129.54	8.4031	0.03	390	2388	100.0	38.99	23.4130

5 rows × 26 columns

#Importing True RUL of engines of Test data



y_true = pd.read_csv('C:\\Users\\Madhu Shree\\OneDrive\\Desktop\\Generative Model\\data\\CMAPSSData\\RUL_FD001.txt',delim_whitespace=True,names=["RUL"])
y_true["UnitNumber"] = y_true.index
y_true.head()

C:\Users\Madhu Shree\AppData\Local\Temp\ipykernel_9432\567814418.py:5: FutureWarning: The 'delim_whitespace' keyword in pd.read_csv is deprecated and will be removed in a future version. Use ``sep='\s+'`` instead
  y_true = pd.read_csv('C:\\Users\\Madhu Shree\\OneDrive\\Desktop\\Generative Model\\data\\CMAPSSData\\RUL_FD001.txt',delim_whitespace=True,names=["RUL"])

	RUL	UnitNumber
0	112	0
1	98	1
2	69	2
3	82	3
4	91	4

Data Analysis

#shape of the train data
df_train.shape

(20631, 27)

#Finding the missing values
df_train.isnull().sum()

UnitNumber    0
Cycle         0
mode1         0
mode2         0
mode3         0
sensor1       0
sensor2       0
sensor3       0
sensor4       0
sensor5       0
sensor6       0
sensor7       0
sensor8       0
sensor9       0
sensor10      0
sensor11      0
sensor12      0
sensor13      0
sensor14      0
sensor15      0
sensor16      0
sensor17      0
sensor18      0
sensor19      0
sensor20      0
sensor21      0
RUL           0
dtype: int64

#Unit
df_train.UnitNumber.unique()

array([  1,   2,   3,   4,   5,   6,   7,   8,   9,  10,  11,  12,  13,
        14,  15,  16,  17,  18,  19,  20,  21,  22,  23,  24,  25,  26,
        27,  28,  29,  30,  31,  32,  33,  34,  35,  36,  37,  38,  39,
        40,  41,  42,  43,  44,  45,  46,  47,  48,  49,  50,  51,  52,
        53,  54,  55,  56,  57,  58,  59,  60,  61,  62,  63,  64,  65,
        66,  67,  68,  69,  70,  71,  72,  73,  74,  75,  76,  77,  78,
        79,  80,  81,  82,  83,  84,  85,  86,  87,  88,  89,  90,  91,
        92,  93,  94,  95,  96,  97,  98,  99, 100], dtype=int64)

#Engines having maximum life

df_train[["UnitNumber","Cycle"]].groupby("UnitNumber").max().sort_values(by = ["Cycle"], ascending= False).head(5)

	Cycle
UnitNumber
69	362
92	341
96	336
67	313
83	293

Mode Setting

#Visualizing Mode Setting of units 1 to 15.

fig,ax=plt.subplots(1,3,figsize=(30,8),sharex='all')
for i in range(0,3):
    df_u1=df_train.query('UnitNumber==2').reset_index(drop = True)
    df_u1['rolling_avg'] = df_u1['mode'+str(i+1)].rolling(window = 5).mean()
    df_u1['rolling_avg'].plot(kind = "line", ax = ax[i])
    ax[i].set_title('mode'+str(i+1))
    ax[i].set_xlabel("Cycle")

#Mode1

fig, axes = plt.subplots(nrows = 5, ncols = 3, figsize = (25,25))

ax = axes.ravel()

for i in range(0,15):
    temp = df_train.mode1[df_train.UnitNumber == i+1].reset_index(drop = True).rolling(window = 5).mean()
    temp.plot(kind = "line", ax = ax[i])
    ax[i].set_title('Unit'+str(i+1))
    ax[i].set_xlabel("Cycle")

#Mode2

fig, axes = plt.subplots(nrows = 5, ncols = 3, figsize = (25,25))

ax = axes.ravel()

for i in range(0,15):
    temp = df_train.mode2[df_train.UnitNumber == i+1].reset_index(drop = True).rolling(window = 5).mean()
    temp.plot(kind = "line", ax = ax[i])
    ax[i].set_title('Unit'+str(i+1))
    ax[i].set_xlabel("Cycle")

#Mode3

fig, axes = plt.subplots(nrows = 5, ncols = 3, figsize = (25,25))

ax = axes.ravel()

for i in range(0,15):
    temp = df_train.mode3[df_train.UnitNumber == i+1].reset_index(drop = True).rolling(window = 5).mean()
    temp.plot(kind = "line", ax = ax[i])
    ax[i].set_title('Unit'+str(i+1))
    ax[i].set_xlabel("Cycle")

fig,ax=plt.subplots(7,3,figsize=(30,20),sharex=True)
df_u1=df_train.query('UnitNumber==5')
c=0
for i in range(0,7):
    for j in range(0,3):
        ax[i,j].plot(df_u1.Cycle.values, df_u1['sensor'+str(c+1)])
        ax[i,j].set_title('sensor'+str(c+1))
        ax[i,j].axvline(0,c='r')
        c+=1
plt.suptitle('Sensor Traces: Unit 5',fontsize=50)
plt.show()

#Sensor Measure 6

fig, axes = plt.subplots(nrows = 5, ncols = 3, figsize = (25,25))

ax = axes.ravel()

for i in range(0,15):
    temp = df_train.sensor6[df_train.UnitNumber == i+1].reset_index(drop = True)
    temp.plot(kind = "line", ax = ax[i])
    ax[i].set_title('Unit'+str(i+1))
    ax[i].set_xlabel("Cycle")

# necessary features for analysis
not_required_feats = ["sensors1", "sensors5", "sensors6", "sensors10", 
                      "sensors16", "sensors18", "sensors19"]
feats = [feat for feat in sensor_measure_columns_names if feat not in not_required_feats]
feats

['sensor1',
 'sensor2',
 'sensor3',
 'sensor4',
 'sensor5',
 'sensor6',
 'sensor7',
 'sensor8',
 'sensor9',
 'sensor10',
 'sensor11',
 'sensor12',
 'sensor13',
 'sensor14',
 'sensor15',
 'sensor16',
 'sensor17',
 'sensor18',
 'sensor19',
 'sensor20',
 'sensor21']

#Correlation Analysis

corr = df_train[feats + ["RUL"]].corr()

fig = plt.figure(figsize=(12,12))
ax = fig.add_subplot(111)
ax = sns.heatmap(corr, annot=True, cmap = "coolwarm", fmt=".2f")